Comparing 2 models

DeepSeek V4.1 Flash vs Gemini 3.1 Pro Preview

Benchmarks through

Verdict

DeepSeek V4.1 Flash and Gemini 3.1 Pro Preview are not yet ranked on the same task, so compare the specifications below. DeepSeek V4.1 Flash costs 39.4x less per input token. Only DeepSeek V4.1 Flash has open weights for self-hosting.

  • Choose DeepSeek V4.1 Flash for you need to self-host.

Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.

metric
Model 1DeepSeek V4.1 Flash
Model 2Gemini 3.1 Pro Preview
Best for
JSON & Schema Output (#1)
Business Writing (#3)
Provider
deepseek
google
Context
1.0MBest
1.0MBest
Input / 1M
$0.051Best
$2
Output / 1M
$0.20Best
$12
Tool use
yesBest
yesBest
Vision
yesBest
yesBest
Reasoning
yesBest
yesBest
Open-weight
yesBest
—
Released
Sep 10, 2026
Feb 19, 2026

Measured head to head

Benchmarks both models were run on

EvaluationDeepSeek V4.1 FlashGemini 3.1 Pro PreviewSource
FrontierMath Tiers 1-3 (Epoch AI)67.4% ± 2.859.6% ± 2.9source · 2026-10-08
GPQA Diamond (Epoch AI)89.8% ± 1.794.1% ± 1.7source · 2026-10-09
LiveBench Agentic Coding77.3%44.1%source · 2026-10-18
LiveBench Coding80.0%76.5%source · 2026-10-18
LiveBench Data Analysis79.3%78.5%source · 2026-10-18
LiveBench Instruction Following70.0%79.1%source · 2026-10-18
LiveBench Language81.2%85.4%source · 2026-10-18
LiveBench Math93.3%91.0%source · 2026-10-18
LiveBench Reasoning86.7%84%source · 2026-10-18
LMArena Agent Bash Recovery7.9-23.3source · 2026-10-08
LMArena Creative Writing1438 Elo1483 Elosource · 2026-11-11
LMArena Instruction Following1473 Elo1465 Elosource · 2026-11-11
LMArena Long Query1474 Elo1482 Elosource · 2026-11-11
LMArena Math1479 Elo1485 Elosource · 2026-11-11
LMArena Text1475 Elo1487 Elosource · 2026-11-11
LMArena Text Factuality1468 Elo1472 Elosource · 2026-11-11
LMArena Vision1263 Elo1280 Elosource · 2026-11-09
LMArena Vision Diagrams1296 Elo1309 Elosource · 2026-11-09
LMArena Vision OCR1274 Elo1295 Elosource · 2026-11-09
LMArena WebDev1621 Elo1446 Elosource · 2026-11-11
LMArena WebDev Image-to-Web1610 Elo1480 Elosource · 2026-11-10
OTIS Mock AIME (Epoch AI)98.3% ± 0.695.6% ± 3.1source · 2026-10-08
SimpleQA Verified (Epoch AI)42.9% ± 1.673.5% ± 1.4source · 2026-10-13

Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.